© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42607
    Prev
    Next
    INDEX
    Explanations

    mathematical constants involving pi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åıĪ大
    -0.08
    ä¸Ń央åħ«é¡¹è§Ħå®ļ
    -0.08
    agl
    -0.08
    /entity
    -0.07
    peng
    -0.07
    elik
    -0.07
    ActionResult
    -0.07
    ToBounds
    -0.07
    alytics
    -0.07
    asco
    -0.07
    POSITIVE LOGITS
    丹
    0.07
    oker
    0.06
    haft
    0.06
    oven
    0.06
    ces
    0.06
    _GP
    0.06
    inc
    0.06
    sumer
    0.06
    ardo
    0.06
    helper
    0.06
    Activations Density 0.002%

    No Known Activations